Spatially and spectrally consistent deep functional maps
Cycle consistency has long been exploited as a powerful prior for jointly optimizing maps
within a collection of shapes. In this paper, we investigate its utility in the approaches of …
within a collection of shapes. In this paper, we investigate its utility in the approaches of …
Self-supervised learning for multimodal non-rigid 3d shape matching
The matching of 3D shapes has been extensively studied for shapes represented as surface
meshes, as well as for shapes represented as point clouds. While point clouds are a …
meshes, as well as for shapes represented as point clouds. While point clouds are a …
Partial matching of nonrigid shapes by learning piecewise smooth functions
D Bensaïd, N Rotstein, N Goldenstein… - Computer Graphics …, 2023 - Wiley Online Library
Learning functions defined on non‐flat domains, such as outer surfaces of non‐rigid shapes,
is a central task in computer vision and geometry processing. Recent studies have explored …
is a central task in computer vision and geometry processing. Recent studies have explored …
Memory-Scalable and Simplified Functional Map Learning
Deep functional maps have emerged in recent years as a prominent learning-based
framework for non-rigid shape matching problems. While early methods in this domain only …
framework for non-rigid shape matching problems. While early methods in this domain only …